Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    file paths and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Defensive
    -0.07
    BK
    -0.07
     faç
    -0.07
     *,
    -0.07
     trú
    -0.07
     своем
    -0.07
     Based
    -0.06
    _deg
    -0.06
    mploy
    -0.06
     Geg
    -0.06
    POSITIVE LOGITS
    城市
    0.08
     copies
    0.07
    液
    0.07
    โหลด
    0.07
     stations
    0.07
     hall
    0.06
    Human
    0.06
     archive
    0.06
    __':↵
    0.06
    .symbol
    0.06
    Act Density 0.005%

    No Known Activations